Mapping the Potential Distribution of Oak Wilt (Bretziella fagacearum) in East Central and Southeast Minnesota Using Maxent

Abstract With the advancement of spatial analysis and remote sensing technology, potentially devastating forest pathogens can be managed through spatial modeling. This study used Maxent, a presence-only species-distribution model, to map the potential probability distribution of the invasive forest pathogen oak wilt (Bretziella fagacearum) in eastern and southeastern Minnesota. The model related oak wilt occurrence data to environmental variables including climate, topography, land cover, soil, and population density. Results showed that areas with the highest probability of oak wilt occur within and surrounding the Minneapolis/St. Paul metropolitan area. The jackknife test of variable importance indicated land cover and soil type as important variables contributing to the prediction of the distribution. Multiple methods of analysis showed that the model performed better than random at predicting the occurrence of oak wilt. This study shows Maxent’s potential as an accurate tool in the early detection and management of forest diseases.

Download Full-text

Spatial and Temporal Epidemiologic features analysis of pulmonary tuberculosis in Nanjing, China

10.21203/rs.2.19145/v1 ◽

2019 ◽

Author(s):

Hongyu Zhao ◽

Changkui Sun ◽

Wei Ma ◽

Guoping Yin ◽

Xia Zhang ◽

...

Keyword(s):

Risk Factors ◽

Environmental Factors ◽

Species Distribution ◽

Species Distribution Model ◽

Central City ◽

Floating Population ◽

Distribution Model ◽

Jackknife Test ◽

Factors Associated ◽

Epidemiologic Features

Abstract Background This study aims to analyse the epidemiological features of tuberculosis in Nanjing and to identify possible risk factors associated with the spatial-temporal distribution.Methods Firstly, we used descriptive statistical method to study the epidemiologic features of confirmed PTB cases in 2017. Secondly, we explored Maxent method to construct the species distribution model with a high spatial resolution of 1km based on those confirmed cases and environmental features. Once again, we validated the performance of the species distribution model using ROC approach and spatial jackknife test, identified the key environmental factors associated with PTB occurrence. Finally, we created a prediction map under specific environmental factors by projecting the training model onto the research areas.Results The seasonal amount of PTB was not obvious. The key risk factors associated with PTB occurrence are monthly mean vapor pressure, solar radiation, monthly average temperature, and precipitation with suitable ranges. The economically developed central city is the high-burden area of tuberculosis with a high risk probability, and the economically backward Gaochun district is the high transmission area of tuberculosis with a high incidence. Epidemiologically, the farmers, the elderly, the floating population, and males are the focus groups for PTB prevention and control.Conclusion The combination of environmental factors with Maxent methods is an appropriate option to analyse and estimate the spatial and temporal distribution of PTB cases.

Download Full-text

Climate, soil or both? Which variables are better predictors of the distributions of Australian shrub species?

PeerJ ◽

10.7717/peerj.3446 ◽

2017 ◽

Vol 5 ◽

pp. e3446 ◽

Cited By ~ 15

Author(s):

Yasmin Hageer ◽

Manuel Esperón-Rodríguez ◽

John B. Baumgartner ◽

Linda J. Beaumont

Keyword(s):

Species Richness ◽

Regional Differences ◽

Predictive Power ◽

Species Distribution Model ◽

Wood Products ◽

Distribution Model ◽

Climate Variables ◽

Shrub Species ◽

Soil Variables ◽

Better Than

BackgroundShrubs play a key role in biogeochemical cycles, prevent soil and water erosion, provide forage for livestock, and are a source of food, wood and non-wood products. However, despite their ecological and societal importance, the influence of different environmental variables on shrub distributions remains unclear. We evaluated the influence of climate and soil characteristics, and whether including soil variables improved the performance of a species distribution model (SDM), Maxent.MethodsThis study assessed variation in predictions of environmental suitability for 29 Australian shrub species (representing dominant members of six shrubland classes) due to the use of alternative sets of predictor variables. Models were calibrated with (1) climate variables only, (2) climate and soil variables, and (3) soil variables only.ResultsThe predictive power of SDMs differed substantially across species, but generally models calibrated with both climate and soil data performed better than those calibrated only with climate variables. Models calibrated solely with soil variables were the least accurate. We found regional differences in potential shrub species richness across Australia due to the use of different sets of variables.ConclusionsOur study provides evidence that predicted patterns of species richness may be sensitive to the choice of predictor set when multiple, plausible alternatives exist, and demonstrates the importance of considering soil properties when modeling availability of habitat for plants.

Download Full-text

Influence of Habitat on Presence of Striped Skunks in Midwestern North America

Diversity ◽

10.3390/d13020083 ◽

2021 ◽

Vol 13 (2) ◽

pp. 83

Author(s):

Katelyn Amspacher ◽

F. Agustín Jiménez ◽

Clayton Nielsen

Keyword(s):

North America ◽

Land Cover ◽

Open Space ◽

Forest Cover ◽

Species Distribution Model ◽

Distribution Model ◽

Natural Food ◽

Striped Skunk ◽

Human Modification ◽

Striped Skunks

Striped skunks (Mephitis mephitis) are urban-adapted, generalist mesocarnivores widely distributed throughout North America. Although striped skunks have been studied extensively at small scales, knowledge of habitat influences on striped skunks at large scales is lacking. We developed a species distribution model (SDM) to examine potential striped skunk presence in a 16,058 km2 portion of southern Illinois, USA. We built models using SDM Toolbox and MaxEnt, and incorporated known presence locations, 1 km2 land cover data, and an index of human modification of the landscape. Land cover and human modification explained 98% and 2% of variation in our model, respectively. The highest presence of striped skunks existed in areas with forest cover and developed open space with moderate human modification. The striped skunk presence was lowest in areas with cultivated crops and woody wetlands with either low or high human modification. Forest cover provides natural food and shelter resources for striped skunks, but resources are likely augmented by human activity in developed open space. Cultivated crops only provide seasonal resources, and inundation limits denning in wooded wetlands. Our model indicated striped skunks are a synanthropic species that regularly inhabits both natural and anthropogenic habitats over a large scale.

Download Full-text

A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

Remote Sensing ◽

10.3390/rs13081495 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1495

Author(s):

Jehyeok Rew ◽

Yongjang Cho ◽

Eenjun Hwang

Keyword(s):

Neural Networks ◽

Species Distribution ◽

Best Practice ◽

Deep Neural Networks ◽

Species Distribution Models ◽

Species Distribution Model ◽

Environmental Data ◽

Distribution Model ◽

Distribution Models ◽

Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Download Full-text

Improving performance of species distribution model in mountainous areas with complex topography

Ecological Research ◽

10.1111/1440-1703.12227 ◽

2021 ◽

Author(s):

Chi‐Cheng Liao ◽

Yi‐Huey Chen

Keyword(s):

Species Distribution ◽

Species Distribution Model ◽

Distribution Model ◽

Complex Topography ◽

Mountainous Areas

Download Full-text

A Bioclimate-Based Maximum Entropy Model for Comperiella calauanica Barrion, Almarinez and Amalin (Hymenoptera: Encyrtidae) in the Philippines

Insects ◽

10.3390/insects12010026 ◽

2021 ◽

Vol 12 (1) ◽

pp. 26

Author(s):

Billy Joel M. Almarinez ◽

Mary Jane A. Fadri ◽

Richard Lasina ◽

Mary Angelique A. Tavera ◽

Thaddeus M. Carvajal ◽

...

Keyword(s):

Maximum Entropy ◽

Habitat Suitability ◽

Species Distribution Model ◽

Biological Control Agent ◽

The Philippines ◽

Distribution Model ◽

Field Surveys ◽

Probability Of Occurrence ◽

Precipitation Seasonality ◽

Bioclimatic Variables

Comperiella calauanica is a host-specific endoparasitoid and effective biological control agent of the diaspidid Aspidiotus rigidus, whose outbreak from 2010 to 2015 severely threatened the coconut industry in the Philippines. Using the maximum entropy (Maxent) algorithm, we developed a species distribution model (SDM) for C. calauanica based on 19 bioclimatic variables, using occurrence data obtained mostly from field surveys conducted in A. rigidus-infested areas in Luzon Island from 2014 to 2016. The calculated the area under the ROC curve (AUC) values for the model were very high (0.966, standard deviation = 0.005), indicating the model’s high predictive power. Precipitation seasonality was found to have the highest relative contribution to model development. Response curves produced by Maxent suggested the positive influence of mean temperature of the driest quarter, and negative influence of precipitation of the driest and coldest quarters on habitat suitability. Given that C. calauanica has been found to always occur with A. rigidus in Luzon Island due to high host-specificity, the SDM for the parasitoid may also be considered and used as a predictive model for its host. This was confirmed through field surveys conducted between late 2016 and early 2018, which found and confirmed the occurrence of A. rigidus in three areas predicted by the SDM to have moderate to high habitat suitability or probability of occurrence of C. calauanica: Zamboanga City in Mindanao; Isabela City in Basilan Island; and Tablas Island in Romblon. This validation in the field demonstrated the utility of the bioclimate-based SDM for C. calauanica in predicting habitat suitability or probability of occurrence of A. rigidus in the Philippines.

Download Full-text